基于SVM极点分类的故障诊断与可靠控制

Fault Diagnosis and Control of Static System Based on LIB-SVM

利用SVM分类技术,针对系统故障极点进行分类,利用网格搜寻法,实现对不同故障极点的分类进而实现对系统故障的检测和诊断,为了实现对系统极点变化的实时监测,给出了通过系统状态估计系统极点的新方法.在给出故障诊断的基础上,同时给出了针对相应故障的可靠控制器的设计.最后通过数例验证极点观测器对极点估计的准确性和故障诊断的准确性及可靠控制的有效性.

For linear system ,the extreme observer design, and the use of LIBSVM （A Library for Support Vector Machines）, using a grid search method to select the optimum parameters of the C and g poles design classifier, solve the control problem of single channel fault in the linear system, reduce system energy consumption and conservation. Simulation results show that this method has high diagnostic accuracy and is suitable for the detection and location of the fault of the closed loop system. The simulation results show that the method is effective.